tez-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Hitesh Shah <hit...@apache.org>
Subject Re: Which computation model does Tez supports
Date Wed, 25 Mar 2015 17:38:15 GMT
Not today for sure. But there have been thoughts on how we can make the VertexManager more
powerful. One jira that Gopal filed was to be able to short-circuit processing of a Vertex
when certain conditions are met ( https://issues.apache.org/jira/browse/TEZ-2103 ). This could
then be leveraged in multiple ways. One approach could be for VertexManagers to send events
to downstream Vertices where the respective vertex managers could short-circuit some of their
processing. 

Again, just to be clear, none of this is implemented and the above is just potential hand
waving in terms of what is possible. It really all depends on help from the folks in the community
to work on this if anyone is interested in tackling this aspect. 

thanks
— Hitesh


On Mar 25, 2015, at 10:24 AM, Johannes Zillmann <jzillmann@googlemail.com> wrote:

> Hey Hitesh, thanks for you thoughts!
> 
> In one chooses the multi-vertex approach, i guess there is no simple thing one could
do to achieve n-iterations where n is flexible based on the output of the n-1 iteration.
> So you can’t do 
> - do max 20 iterationos
> - stop in case certain conditions are met
> 
> !?
> 
> Johannes
> 
> 
>> On 25 Mar 2015, at 18:05, Hitesh Shah <hitesh@apache.org> wrote:
>> 
>> Hi Johannes, 
>> 
>> You would likely not avoid it if you went with the approach of multiple DAGs. For
most iterative programs, you do need to checkpoint at some point. The checkpoint would likely
need to be reliable to reduce the amount of re-computation needed if the check pointed data
is lost. An option would be to use something like the HDFS in-memory storage tier ( which
lazily persists to disk ) to reduce the perf overhead. Also, in terms of loop unrolling, a
single DAG could be pre-constructed to run multiple iterations using multiple vertices and
then use the final vertex of the DAG as a checkpointing mechanism after N iterations/vertices.
>> 
>> Also, depending on the amount of data being written out, the overhead of writing
to HDFS may not be too high. Furthermore, with Tez sessions, there is no real overhead of
launching a new DAG ( if some containers are retained ) as compared to trying to do the same
with multiple MR jobs. 
>> 
>> — Hitesh
>> 
>> 
>> On Mar 25, 2015, at 2:02 AM, Johannes Zillmann <jzillmann@googlemail.com> wrote:
>> 
>>> Hey Gopal,
>>> 
>>>> On 25 Mar 2015, at 05:26, Gopal Vijayaraghavan <gopalv@apache.org>
wrote:
>>>> 
>>>> Hi,
>>>> 
>>>> Iterative algorithms are expressed as DAGs in a loop.
>>>> 
>>>> The acyclic nature of DAGs, whether in Tez or Spark (since you mention the
>>>> paper) make that the natural way to implement that - repeated application
>>>> of the same operation over the same data, with a decision condition
>>>> determining whether to stay in the loop or not.
>>> 
>>> Can you point to a piece of code which implements this approach ?
>>> If you each look operation is a single DAG, how would that avoid hdfs barrier
?
>>> 
>>> Johannes
>>> 
>>>> 
>>>> You might want to look at last year¹s Hadoop Summit presentations for a
>>>> direct example of Iterative algorithms with Tez.
>>>> 
>>>> http://www.slideshare.net/Hadoop_Summit/pig-on-tez-low-latency-etl-with-big
>>>> -data/25
>>>> 
>>>> 
>>>> Logistic regression needs you to use a library which implements that
>>>> specific algorithm [1].
>>>> 
>>>> On that note, something which needs incremental iteration can probably be
>>>> even more efficient in Tez than these approaches if you unroll the
>>>> iteration as 1-1 edges all of the final tasks ending up generating outputs.
>>>> 
>>>> Cheers,
>>>> Gopal
>>>> [1] - https://github.com/myui/hivemall#regression
>>>> 
>>>> 
>>>> On 3/24/15, 8:43 PM, "Chang Chen" <baibaichen@gmail.com> wrote:
>>>> 
>>>>> Hi
>>>>> 
>>>>> from the PhD Disseration
>>>>> <http://www.eecs.berkeley.edu/Pubs/TechRpts/2014/EECS-2014-12.pdf>
of
>>>>> Matei
>>>>> Zaharia, there are four computation models in the large scale clusters:
>>>>> 
>>>>> 
>>>>> 1. *Iterative algorithm*, such as graph processing and machine leaning
>>>>> algorithm
>>>>> 2. *Relational query*
>>>>> 3. *MapReduce*, a general parallel computation model
>>>>> 4. *Stream processing*,
>>>>> 
>>>>> Obviously, Tez supports #2 and #3, but for #1 and #4, I don't see any
>>>>> examples.
>>>>> 
>>>>> As for streaming, I guess if we implement appropriate input,  there is
no
>>>>> reason that tez can't support in theory.
>>>>> 
>>>>> But for Machine Leaning, how do we use vertex and edge to express
>>>>> *Logistic
>>>>> Regression*?
>>>>> 
>>>>> Thanks
>>>>> Chang
>>>> 
>>>> 
>>> 
>> 
> 


Mime
View raw message